Identifying work related injuries: comparison of methods for interrogating text fields

Cues Disseminated by Professional Associations That Represent 5 Health Care Professions Across 5 Nations: Lexical Analysis of Tweets

BACKGROUND

Collaboration across health care professions is critical in efficiently and effectively managing complex and chronic health conditions, yet interprofessional care does not happen automatically. Professional associations have a key role in setting a profession's agenda, maintaining professional identity, and establishing priorities. The associations' external communication is commonly undertaken through social media platforms, such as Twitter. Despite the valuable insights potentially available into professional associations through such communication, to date, their messaging has not been examined.

OBJECTIVE

This study aimed to identify the cues disseminated by professional associations that represent 5 health care professions spanning 5 nations.

METHODS

Using a back-iterative application programming interface methodology, public tweets were sourced from professional associations that represent 5 health care professions that have key roles in community-based health care: general practice, nursing, pharmacy, physiotherapy, and social work. Furthermore, the professional associations spanned Australia, Canada, New Zealand, the United Kingdom, and the United States. A lexical analysis was conducted of the tweets using Leximancer (Leximancer Pty Ltd) to clarify relationships within the discourse.

RESULTS

After completing a lexical analysis of 50,638 tweets, 7 key findings were identified. First, the discourse was largely devoid of references to interprofessional care. Second, there was no explicit discourse pertaining to physiotherapists. Third, although all the professions represented in this study support patients, discourse pertaining to general practitioners was most likely to be connected with that pertaining to patients. Fourth, tweets pertaining to pharmacists were most likely to be connected with discourse pertaining to latest and research. Fifth, tweets about social workers were unlikely to be connected with discourse pertaining to health or care. Sixth, notwithstanding a few exceptions, the findings across the different nations were generally similar, suggesting their generality. Seventh and last, tweets pertaining to physiotherapists were most likely to refer to discourse pertaining to profession.

CONCLUSIONS

The findings indicate that health care professional associations do not use Twitter to disseminate cues that reinforce the importance of interprofessional care. Instead, they largely use this platform to emphasize what they individually deem to be important and advance the interests of their respective professions. Therefore, there is considerable opportunity for professional associations to assert how the profession they represent complements other health care professions and how the professionals they represent can enact interprofessional care for the benefit of patients and carers.

The Use and Structure of Emergency Nurses' Triage Narrative Data: Scoping Review

BACKGROUND

Emergency departments use triage to ensure that patients with the highest level of acuity receive care quickly and safely. Triage is typically a nursing process that is documented as structured and unstructured (free text) data. Free-text triage narratives have been studied for specific conditions but never reviewed in a comprehensive manner.

OBJECTIVE

The objective of this paper was to identify and map the academic literature that examines triage narratives. The paper described the types of research conducted, identified gaps in the research, and determined where additional review may be warranted.

METHODS

We conducted a scoping review of unstructured triage narratives. We mapped the literature, described the use of triage narrative data, examined the information available on the form and structure of narratives, highlighted similarities among publications, and identified opportunities for future research.

RESULTS

We screened 18,074 studies published between 1990 and 2022 in CINAHL, MEDLINE, Embase, Cochrane, and ProQuest Central. We identified 0.53% (96/18,074) of studies that directly examined the use of triage nurses' narratives. More than 12 million visits were made to 2438 emergency departments included in the review. In total, 82% (79/96) of these studies were conducted in the United States (43/96, 45%), Australia (31/96, 32%), or Canada (5/96, 5%). Triage narratives were used for research and case identification, as input variables for predictive modeling, and for quality improvement. Overall, 31% (30/96) of the studies offered a description of the triage narrative, including a list of the keywords used (27/96, 28%) or more fulsome descriptions (such as word counts, character counts, abbreviation, etc; 7/96, 7%). We found limited use of reporting guidelines (8/96, 8%).

CONCLUSIONS

The breadth of the identified studies suggests that there is widespread routine collection and research use of triage narrative data. Despite the use of triage narratives as a source of data in studies, the narratives and nurses who generate them are poorly described in the literature, and data reporting is inconsistent. Additional research is needed to describe the structure of triage narratives, determine the best use of triage narratives, and improve the consistent use of triage-specific data reporting guidelines.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

RR2-10.1136/bmjopen-2021-055132.

Cost, profile, and postoperative resource use for surgically managed acute hand and wrist injuries with emergency department presentation

STUDY DESIGN

Retrospective cost-of-illness study.

INTRODUCTION

Injuries to the hand and wrist are common. Most uncomplicated and stable upper extremity injuries recover with conservative management; however, some require surgical intervention. The economic burden on the health care system from such injuries can be considerable.

PURPOSE OF THE STUDY

To estimate the economic implications of surgically managed acute hand and wrist injuries at one urban health care network.

METHODS

Using 33 primary diagnosis ICD-10 codes involving the hand and wrist, 453 consecutive patients from 2014 to 2015 electronic billing records who attended the study setting emergency department and received consequent surgical intervention and outpatient follow-up were identified. Electronic medical records were reviewed to extract demographic data. Costs were calculated from resource use in the emergency department, inpatient, and outpatient settings. Results are presented by demographics, injury type, mechanism of injury, and patient pathway.

RESULTS

Two hundred and twenty-six individuals (n 1⁄4 264 surgeries) were included. The total cost of all injuries was $1,204,606. The median cost per injury for non-compensable cases (n = 191) was $4508 [IQR $3993-$6172] and $5057 [IQR $3957-$6730] for compensable cases (n = 35). The median number of postoperative appointments with a surgeon was 2.00 (IQR 1.00-3.00) for both compensable and non-compensable cases. The number of hand therapy appointments for non-compensable cases and compensable cases was 4 [IQR 2-6] and 2 [IQR 1-3], respectively.

DISCUSSION

Findings of this investigation highlight opportunities for health promotion strategies for reducing avoidable injuries and present considerations for reducing cost burden by addressing high fail to attend (FTA) appointment rates.

CONCLUSION

Surgically managed hand and wrist injuries contribute to a significant financial burden on the health care system. Further research using stringent data collection methods are required to establish epidemiological data and national estimates of cost burden.

National Ambulance Surveillance System: A novel method using coded Australian ambulance clinical records to monitor self-harm and mental health-related morbidity

Self-harm and mental health are inter-related issues that substantially contribute to the global burden of disease. However, measurement of these issues at the population level is problematic. Statistics on suicide can be captured in national cause of death data collected as part of the coroner's review process, however, there is a significant time-lag in the availability of such data, and by definition, these sources do not include non-fatal incidents. Although survey, emergency department, and hospitalisation data present alternative information sources to measure self-harm, such data do not include the richness of information available at the point of incident. This paper describes the mental health and self-harm modules within the National Ambulance Surveillance System (NASS), a unique Australian system for monitoring and mapping mental health and self-harm. Data are sourced from paramedic electronic patient care records provided by Australian state and territory-based ambulance services. A team of specialised research assistants use a purpose-built system to manually scrutinise and code these records. Specific details of each incident are coded, including mental health symptoms and relevant risk indicators, as well as the type, intent, and method of self-harm. NASS provides almost 90 output variables related to self-harm (i.e., type of behaviour, self-injurious intent, and method) and mental health (e.g., mental health symptoms) in the 24 hours preceding each attendance, as well as demographics, temporal and geospatial characteristics, clinical outcomes, co-occurring substance use, and self-reported medical and psychiatric history. NASS provides internationally unique data on self-harm and mental health, with direct implications for translational research, public policy, and clinical practice. This methodology could be replicated in other countries with universal ambulance service provision to inform health policy and service planning.

Description and cost-analysis of emergency department attendances for hand and wrist injuries

BACKGROUND

Injuries to the hand and wrist are estimated to account for between 10% and 30% of all ED presentations. The economic burden placed on the healthcare system can be extensive and rise sharply with increase in injury severity.

OBJECTIVES

This cost-analysis was performed with the aim of estimating the economic implications of ED attendances for hand and wrist injuries from the perspective of one Australian public health network.

METHODS

Data from two EDs were retrieved from the electronic billing records of one large health network across two financial year periods (2014-2015 and 2015-2016) using ICD-10 codes. All costs that resulted from the treatment of any acute hand or wrist injury across the 2 year period were calculated and are presented by age, sex, injury type and mechanism of injury.

RESULTS

A total of 10 024 individuals presented to the two EDs in the 2 year period, accounting for approximately 5.4% of all presentations. The most common presentations were males (62.2%), people aged 25-34 years (26.9%) and lacerations (31.2%). The total cost in the 2 year study period was $3 959 535.38 ($1 923 852.38 in 2014-2015; $2 035 683.00 in 2015-2016). The mean cost per presentation was $383 (95% CI [$373, $393]) in 2014-2015 and $407 (95% CI [$394, $421]) in 2015-2016.

CONCLUSIONS

Acute hand and wrist injuries contribute to a significant volume of ED presentations each year in one Australian public health network leading to significant expenditure and health resources. Further research into how to best utilise resources and reduce avoidable injuries should be priority areas to reduce the cost of these injuries to the healthcare system and society.

Construction accident narrative classification: An evaluation of text mining techniques

Learning from past accidents is fundamental to accident prevention. Thus, accident and near miss reporting are encouraged by organizations and regulators. However, for organizations managing large safety databases, the time taken to accurately classify accident and near miss narratives will be very significant. This study aims to evaluate the utility of various text mining classification techniques in classifying 1000 publicly available construction accident narratives obtained from the US OSHA website. The study evaluated six machine learning algorithms, including support vector machine (SVM), linear regression (LR), random forest (RF), k-nearest neighbor (KNN), decision tree (DT) and Naive Bayes (NB), and found that SVM produced the best performance in classifying the test set of 251 cases. Further experimentation with tokenization of the processed text and non-linear SVM were also conducted. In addition, a grid search was conducted on the hyperparameters of the SVM models. It was found that the best performing classifiers were linear SVM with unigram tokenization and radial basis function (RBF) SVM with uni-gram tokenization. In view of its relative simplicity, the linear SVM is recommended. Across the 11 labels of accident causes or types, the precision of the linear SVM ranged from 0.5 to 1, recall ranged from 0.36 to 0.9 and F1 score was between 0.45 and 0.92. The reasons for misclassification were discussed and suggestions on ways to improve the performance were provided.

Machine learning approaches to analysing textual injury surveillance data: a systematic review

OBJECTIVE

To synthesise recent research on the use of machine learning approaches to mining textual injury surveillance data.

DESIGN

Systematic review.

DATA SOURCES

The electronic databases which were searched included PubMed, Cinahl, Medline, Google Scholar, and Proquest. The bibliography of all relevant articles was examined and associated articles were identified using a snowballing technique.

SELECTION CRITERIA

For inclusion, articles were required to meet the following criteria: (a) used a health-related database, (b) focused on injury-related cases, AND used machine learning approaches to analyse textual data.

METHODS

The papers identified through the search were screened resulting in 16 papers selected for review. Articles were reviewed to describe the databases and methodology used, the strength and limitations of different techniques, and quality assurance approaches used. Due to heterogeneity between studies meta-analysis was not performed.

RESULTS

Occupational injuries were the focus of half of the machine learning studies and the most common methods described were Bayesian probability or Bayesian network based methods to either predict injury categories or extract common injury scenarios. Models were evaluated through either comparison with gold standard data or content expert evaluation or statistical measures of quality. Machine learning was found to provide high precision and accuracy when predicting a small number of categories, was valuable for visualisation of injury patterns and prediction of future outcomes. However, difficulties related to generalizability, source data quality, complexity of models and integration of content and technical knowledge were discussed.

CONCLUSIONS

The use of narrative text for injury surveillance has grown in popularity, complexity and quality over recent years. With advances in data mining techniques, increased capacity for analysis of large databases, and involvement of computer scientists in the injury prevention field, along with more comprehensive use and description of quality assurance methods in text mining approaches, it is likely that we will see a continued growth and advancement in knowledge of text mining in the injury field.